Beginner level Deep Learning and Applied AI

Build Neural Networks with PyTorch

Learn how neural networks learn by building them yourself in PyTorch: tensors, gradients, training loops, data pipelines, evaluation and convolutional networks, finishing with an image classifier you can explain and defend.

  • 40hours of work
  • 19parts
  • Checkedcapstone
  • Lifetimeaccess
  • PyTorch
  • Neural networks
  • Gradient descent
  • Model evaluation
  • Image classification
  • Experiment tracking

At a glance

Who it is for

Learners who know basic Python and school-level maths and want to understand deep learning by building it, not just calling a library.

Before you start

Python (functions, lists, classes), NumPy basics are helpful, and school algebra (slope, derivative as rate of change). Python 3.10+ with PyTorch installed from pytorch.org (CPU is enough; a free cloud notebook with a GPU is optional).

How you finish

Pass the quizzes, complete the labs and submit your capstone. Everything is checked as you go and your certificate is issued the moment you finish.

What you will be able to do

  1. 01Explain how a network learns using loss, gradients and gradient descent
  2. 02Write a complete PyTorch training and evaluation loop
  3. 03Load data with Dataset and DataLoader and split it correctly
  4. 04Recognise and reduce overfitting, and report metrics honestly
  5. 05Build, train, save and use a convolutional image classifier

Curriculum 40 hours in 19 parts

Select a kind to highlight its parts.

Stage 1A regression model on real data with a full training loop7 parts · 11 h
  1. 1
    What deep learning is, and tensorsLesson · Short, focused reading with questions to check yourself.
    1 hFree
  2. 2
    Gradients and gradient descentLesson · Short, focused reading with questions to check yourself.
    1 h
  3. 3
    Fit lines and curves by gradient descentWorkshop · Follow along and build, with the steps and the traps written out.
    2 h
  4. 4
    Neural networks: layers, activations and lossesLesson · Short, focused reading with questions to check yourself.
    1 h
  5. 5
    Classify a spiral with a neural networkWorkshop · Follow along and build, with the steps and the traps written out.
    2 h
  6. 6
    Check yourself: tensors, gradients and networksQuiz · Twelve questions, marked at once, with the reason behind each answer.
    1 h
  7. 7
    A regression model on real data with a full training loopLab · Hands-on work. Many labs are checked automatically against what must exist.
    3 h
Stage 2Build and evaluate an image classifier6 parts · 10 h
  1. 8
    Datasets, DataLoaders and splitting data correctlyLesson · Short, focused reading with questions to check yourself.
    1 h
  2. 9
    An image classifier for clothingWorkshop · Follow along and build, with the steps and the traps written out.
    2 h
  3. 10
    Training well: overfitting, regularisation and metricsLesson · Short, focused reading with questions to check yourself.
    1 h
  4. 11
    Diagnose training curves and fix overfittingWorkshop · Follow along and build, with the steps and the traps written out.
    2 h
  5. 12
    Check yourself: data, overfitting and evaluationQuiz · Twelve questions, marked at once, with the reason behind each answer.
    1 h
  6. 13
    Build and evaluate an image classifierLab · Hands-on work. Many labs are checked automatically against what must exist.
    3 h
Stage 3A CNN with augmentation and honest evaluation4 parts · 8 h
  1. 14
    Convolutional networks, saving and using a modelWorkshop · Follow along and build, with the steps and the traps written out.
    2 h
  2. 15
    Experiment tracking, model cards and responsible AIWorkshop · Follow along and build, with the steps and the traps written out.
    2 h
  3. 16
    Check yourself: convolutional networks, saving models and responsible AIQuiz · Twelve questions, marked at once, with the reason behind each answer.
    1 h
  4. 17
    A CNN with augmentation and honest evaluationLab · Hands-on work. Many labs are checked automatically against what must exist.
    3 h
Stage 4Package the model as a command-line tool with a model card1 part · 3 h
  1. 18
    Package the model as a command-line tool with a model cardLab · Hands-on work. Many labs are checked automatically against what must exist.
    3 h
FinishCapstone project1 part · 8 h
  1. 19
    An end-to-end deep learning projectCapstone · A full project for your portfolio.
    8 h
Free lessonWhat deep learning is, and tensors
What you take away

An internship certificate with your skills on it.

Made for you automatically when you finish the last part, it names the internship programme, the level and the 40 hours, lists what you showed, and carries a number and a QR code. Anyone can check it on the NIBVEDA verification page, and it shows as withdrawn there if it is ever revoked.

  • Proof you completed all 40 hours of this internship programme
  • An Internship badge for your profile, CV or portfolio
  • Not a job, a stipend or an academic degree, and it says so

See how verification works

More in Deep Learning and Applied AI

Keep building.

3 programmes in this track, from beginner to expert. Buy the learning path and save 15%.

IntermediateIntermediate40 h Transfer Learning in Practice

Build practical vision and language systems with pretrained models: transfer learning for images, object detection, text classification with transformers, efficient training and a served model with tests and a latency report.

  • Transfer learning
  • Computer vision
  • Transformers and NLP
Rs. 699 + GST
ExpertExpert40 h LLM Applications, Retrieval and Evaluation

Engineer reliable applications on top of large language models: prompting and structured output, retrieval-augmented generation, evaluation harnesses, tool-using agents, security and red-teaming, and cost, latency and quality trade-offs in production.

  • LLM application design
  • Retrieval-augmented generation
  • Evaluation harnesses
Rs. 999 + GST

See all 3 programmes in Deep Learning and Applied AI Take the placement test

Before you enrol

Quick answers.

The policies have the full detail.

Refund policy Terms of use

Is this a real internship?

It is a virtual internship programme: a structured, self-paced course built around a real project, with checked assessments and a certificate. It is not employment, it does not carry a stipend and it is not an academic or AICTE-approved qualification. What it gives you is verified, project-based evidence of skills.

How does self-paced work?

You start when you like and move at your own speed. Each part unlocks when you finish the one before it. There are no live classes and no deadlines. Your access is shown on each programme page.

How is my work checked?

Quizzes are marked as soon as you submit them. Labs use a tick-list of tasks. Intermediate and Expert programmes finish with a capstone that the NIBVEDA team reviews and either accepts or sends back with comments.

Can I get a refund?

Please read the refund policy before you buy. It explains when a refund is possible.

Ready to start?

Rs. 411.82 including GST. Lifetime access. Read the first lesson free before you decide.

Compare programmes